Sentiment Analysis Approach Research Articles

A machine learning approach for Urdu text sentiment analysis

Product evaluations, ratings, and other sorts of online expressions have risen in popularity as a result of the emergence of social networking sites and blogs. Sentiment analysis has emerged as a new area of study for computational linguists as a result of this rapidly expanding data set. From around a decade ago, this has been a topic of discussion for English speakers. However, the scientific community completely ignores other important languages, such as Urdu. Morphologically, Urdu is one of the most complex languages in the world. For this reason, a variety of unique characteristics, such as the language's unusual morphology and unrestricted word order, make the Urdu language processing a difficult challenge to solve. This research provides a new framework for the categorization of Urdu language sentiments. The main contributions of the research are to show how important this multidimensional research problem is as well as its technical parts, such as the parsing algorithm, corpus, lexicon, etc. A new approach for Urdu text sentiment analysis including data gathering, pre-processing, feature extraction, feature vector formation, and finally, sentiment classification has been designed to deal with Urdu language sentiments. The result and discussion section provides a comprehensive comparison of the proposed work with the standard baseline method in terms of precision, recall, f-measure, and accuracy of three different types of datasets. In the overall comparison of the models, the proposed work shows an encouraging achievement in terms of accuracy and other metrics. Last but not least, this section also provides the featured trend and possible direction of the current work.

Sentiment analysis on images using convolutional neural networks based Inception-V3 transfer learning approach

Sentiment analysis has become a precious tool for businesses because it can be used in so many ways: to find out what customers think about products and services, to build customer relationships and loyalty, to improve customer service, and to use emotional marketing. Over the last several years, developing an end-to-end image sentiment analysis approach has significantly emphasized transfer learning methods. Deep learning algorithms have been proven to achieve remarkable outcomes across a broad spectrum of applications. Examining feelings conveyed by images is complex, but there is much space for development. A technique known as Inception-v3 that can readily focus on large portions of the body, such as a person's face, offers a significant advantage compared to the work that was done in the past. This study makes use of Inception-v3, which is a well-known deep convolutional neural network, in addition to extra deep characteristics, to increase the performance of image categorization. A CNN-based Inception-v3 architecture is employed for emotion detection and classification. The datasets CK+, FER2013, and JAFFE are used in this process. The findings are also compared with various well-known machine learning approaches, and the results obtained by the suggested model are superior. The research indicates that the proposed method can reach an accuracy level of 99.5%. The proposed approach can be used in many business applications such as Information Management, Sales, Marketing, User Interaction, Healthcare, Education, Finance, Public Monitoring, Digital PR, etc.

Analysis of Recognition of Twitter Posts using a Hybrid Machine Learning Approach

Sentiment analysis of tweets has become a crucial task in understanding public opinion, sentiment trends, and brand perception. With the exponential growth of social media data, efficient and accurate sentiment analysis methods are essential. This research paper presents a comprehensive study on the design, simulation, and assessment of sentiment analysis of tweets using an improved machine learning methodology. The proposed methodology combines the strengths of natural language processing techniques and advanced machine learning algorithms to achieve superior performance in sentiment classificationIn the introduction, the paper outlines the significance of sentiment analysis and its applications in various domains. It discusses the challenges faced by traditional sentiment analysis approaches and highlights the need for more robust and accurate methodologies. The paper then delves into related works, exploring the existing state-of-the-art techniques and identifying gaps that the proposed methodology aims to address.The proposed methodology section details the steps involved in the sentiment analysis pipeline. It begins with data preprocessing, including tokenization, stop-word removal, and stemming. Feature extraction methods, such as TF-IDF and word embeddings, are explored and compared. Next, the paper presents an improved machine learning algorithm that combines ensemble learning and deep learning techniques. The model's architecture and training process are elaborated, along with the parameter tuning strategies to optimize performance.The results indicate that the proposed methodology outperforms traditional sentiment analysis approaches, achieving higher accuracy and robustness in sentiment classification. The paper highlights the model's strengths in handling sarcasm, irony, and context-specific language, which are common challenges in sentiment analysis. Furthermore, the efficiency of the proposed methodology is demonstrated through its ability to handle large-scale datasets in real-time. In conclusion, this research paper emphasizes the importance of sentiment analysis in understanding public opinion and its role in decision-making processes for businesses and governments. The proposed methodology exhibits promising results, making it a viable solution for sentiment analysis of tweets and other social media data. The study concludes by suggesting future research directions to further enhance sentiment analysis techniques and address emerging challenges in the field.

Dynamic impacts of online investor sentiment on international crude oil prices

In recent years, international crude oil prices have been subject to unusually high fluctuations due to the ravages of the COVID-19 epidemic. Under such extreme market conditions, online investor sentiment can strengthen the correlation between oil price changes and external events. We use a (rolling-window) structural vector autoregression method to investigate the dynamic impact of online investor sentiment on WTI crude oil prices before and after the COVID-19 pandemic across multiple topics of price, supply, demand, and so on, which aims to explore the fluctuation mechanism driven by sentiment and the price changes triggered by public health events. The proposed aspect-level sentiment analysis approach can effectively distinguish and measure sentiment scores of different aspects of the oil market. Our results show that the constructed oil price prosperity index contributes 49.84% to the long-term fluctuations of WTI oil price, ranking first among the influencing factors considered. In addition, the peak value of impulse shocks to WTI oil prices rose from 6.47% to 8.40% during the period of dramatic price volatility caused by the epidemic. The results sketch the mechanisms by which investor sentiment can affect crude oil prices, which help policymakers and investors protect against extreme risks in the oil market.

Discovering fans and anti-fans among social media users based on their emotional reactions and comments

While audience profiling has been a critical concern in social media marketing, little research has used a systematic methodology to identify fans and anti-fans in social media communities. This study aimed to develop a fan and anti-fan detection model by analysing social media users’ mood responses and comments on fan page posts. The sentiment analysis of comments was conducted using a bidirectional long short-term memory (LSTM) model. A total of 83 posts, 849,820 emoticons and 216,688 comments were collected from two different fan pages over 14 days. Results showed that the proposed model, combining emotional reaction analysis and sentiment analysis of their comments, exhibited better fan and anti-fan identification capability than the single-dimensional behaviour model. It exhibited 96% accuracy, 100% precision and 93% recall in terms of community management. This study provides a novel, accurate and efficient way to identify fans and anti-fans that can help form more targeted marketing strategies for social media managers in a cost-effective manner.

Sentiment analysis of clinical narratives: A scoping review

A clinical sentiment is a judgment, thought or attitude promoted by an observation with respect to the health of an individual. Sentiment analysis has drawn attention in the healthcare domain for secondary use of data from clinical narratives, with a variety of applications including predicting the likelihood of emerging mental illnesses or clinical outcomes. The current state of research has not yet been summarized. This study presents results from a scoping review aiming at providing an overview of sentiment analysis of clinical narratives in order to summarize existing research and identify open research gaps. The scoping review was carried out in line with the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) guideline. Studies were identified by searching 4 electronic databases (e.g., PubMed, IEEE Xplore) in addition to conducting backward and forward reference list checking of the included studies. We extracted information on use cases, methods and tools applied, used datasets and performance of the sentiment analysis approach. Of 1,200 citations retrieved, 29 unique studies were included in the review covering a period of 8 years. Most studies apply general domain tools (e.g. TextBlob) and sentiment lexicons (e.g. SentiWordNet) for realizing use cases such as prediction of clinical outcomes; others proposed new domain-specific sentiment analysis approaches based on machine learning. Accuracy values between 71.5–88.2% are reported. Data used for evaluation and test are often retrieved from MIMIC databases or i2b2 challenges. Latest developments related to artificial neural networks are not yet fully considered in this domain. We conclude that future research should focus on developing a gold standard sentiment lexicon, adapted to the specific characteristics of clinical narratives. Efforts have to be made to either augment existing or create new high-quality labeled data sets of clinical narratives. Last, the suitability of state-of-the-art machine learning methods for natural language processing and in particular transformer-based models should be investigated for their application for sentiment analysis of clinical narratives.

A natural language processing approach to uncover patterns among online ratings of otolaryngologists.

Patients increasingly use physician rating websites to evaluate and choose potential healthcare providers. A sentiment analysis and machine learning approach can uniquely analyse written prose to quantitatively describe patients' perspectives from interactions with their physicians. Online written reviews and star scores were analysed from Healthgrades.com using a natural language processing sentiment analysis package. Demographics of otolaryngologists were compared and a multivariable regression for individual words was performed. This study analysed 18 546 online reviews of 1240 otolaryngologists across the USA. Younger otolaryngologists (aged less than 40 years) had higher sentiment and star scores compared with older otolaryngologists (p < 0.001). Male otolaryngologists had higher sentiment and star scores compared with female otolaryngologists (p < 0.001). 'Confident', 'kind', 'recommend' and 'comfortable' were words associated with positive reviews (p < 0.001). Positive bedside manner was strongly reflected in better reviews, and younger age and male gender of the otolaryngologist were associated with better sentiment and star scores.

Evaluation of Deep Learning Approaches for Sentiment Analysis

Due to the increasing popularity of posting evaluations, sentiment analysis has grown to be a crucial area of study. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM (Long Short-Term Memory), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and GRU (Gated Recurrent Unit). Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. To discover the optimal deep learning methodology for the given data, authors here proposed many deep learning methodologies for text data on sentiment analysis. A publicly available dataset including both positive and negative reviews on LSTM, CNN, RNN, and GRU was used in the experiments, and the findings showed that CNN had the highest accuracy compared to the other models. Based on the experimental results of CNN, it was found that prediction from the proposed work exhibited a significant improvement over existing work.

The Influence of Social Media on Cryptocurrency Price: A Sentiment Analysis Approach

The Influence of Social Media on Cryptocurrency Price: A Sentiment Analysis Approach

Curtailing fake news creation and dissemination in Nigeria: Twitter social network and sentiment analysis approaches

Influencers create and facilitate dissemination of information in a network and can shape the attitudes and beliefs of members of a social network. Identifying the influencers and their relations, as well as the sentiment of tweets being disseminated in the network on some selected keywords can help curtail fake news creation and dissemination in the network. This study uses a sequential mixed-methods design with a quantitative method followed by qualitative methods. The quantitative data were collected using Mozdeh big data analysis software. Mozdeh software was used to collect tweets through Twitter’s Streaming application programming interface to build a corpus of tweets, collected from 1 January 2016 to 30 June 2021. The study found two major actors/influencers involved in the creation and dissemination of fake news on the tweeter social network studied. The study further found overall Av. Pos. − Av. Neg. was −0.9935. Data collected were on some specific trending keywords on a particular region in Nigeria. Identifying and monitoring the tweets of influencers in a network can aid in debunking fake news immediately after dissemination and discourage the use of offensive words in tweets. The results revealed major influencers responsible for creating and disseminating fake news on some trending issues in Nigeria.

THE RELEVANCE OF SUSTAINABILITY IN DAY TO LIVING BY WAY OF ORGANIC CONSUMPTION: A DETAILED STUDY ON THE CONSUMER BUYING BEHAVIOUR OF ORGANIC PRODUCTS IN MUMBAI.

Organic products like body care or food products are trending in the market for their originality, nutritional value and long term benefits to its users or consumers. Though this trend is observed we are keen to know about the exact sentiments or feelings of consumers while purchasing the products and after using them. Are these products successful in building their organic value and consumers positive perception towards them? What are the trust building or reducing factors for these organic products? And many other aspects of consumer behavior in order to understand their motive and motivation behind selecting organic products and services. This paper is our sincere effort towards understanding the position of these organic products in consumers mind and in actual market through the consumer behavior sentiment analysis approach. KEYWORDS: Organic product, Consumer Behavior, Health benefits, Consumer Perception, Organic Retailing. Organic food, Sustainable living.

Temporal analysis and opinion dynamics of COVID-19 vaccination tweets using diverse feature engineering techniques.

The outbreak of the COVID-19 pandemic has also triggered a tsunami of news, instructions, and precautionary measures related to the disease on social media platforms. Despite the considerable support on social media, a large number of fake propaganda and conspiracies are also circulated. People also reacted to COVID-19 vaccination on social media and expressed their opinions, perceptions, and conceptions. The present research work aims to explore the opinion dynamics of the general public about COVID-19 vaccination to help the administration authorities to devise policies to increase vaccination acceptance. For this purpose, a framework is proposed to perform sentiment analysis of COVID-19 vaccination-related tweets. The influence of term frequency-inverse document frequency, bag of words (BoW), Word2Vec, and combination of TF-IDF and BoW are explored with classifiers including random forest, gradient boosting machine, extra tree classifier (ETC), logistic regression, Naïve Bayes, stochastic gradient descent, multilayer perceptron, convolutional neural network (CNN), bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), and recurrent neural network (RNN). Results reveal that ETC outperforms using BoW with a 92% of accuracy and is the most suitable approach for sentiment analysis of COVID-19-related tweets. Opinion dynamics show that sentiments in favor of vaccination have increased over time.

Improving Sentiment Prediction of Textual Tweets Using Feature Fusion and Deep Machine Ensemble Model

Widespread fear and panic has emerged about COVID-19 on social media platforms which are often supported by falsified and altered content. This mass hysteria creates public anxiety due to misinformation, misunderstandings, and ignorance of the impact of COVID-19. To assist health professionals in addressing this epidemic more appropriately at the onset, sentiment analysis can potentially help the authorities for devising appropriate strategies. This study analyzes tweets related to COVID-19 using a machine learning approach and offers a high-accuracy solution. Experiments are performed involving different machine and deep learning models along with various features such as Word2vec, term-frequency, term-frequency document frequency, and feature fusion of both feature-generating approaches. The proposed approach combines the extra tree classifier and convolutional neural network and uses feature fusion to achieve the highest accuracy score of 99%. The proposed approach obtains far better results than existing sentiment analysis approaches.

Sentiment analysis and emotion detection of post-COVID educational Tweets: Jordan case.

Education evolved dramatically under Covid-19, and owing to the conditions, distant learning became mandatory. However, this has opened new realities to the educational business under the label of "Hybrid-Learning," where educational institutions are still using online learning in addition to face-to-face learning, which has changed people's lives and split their opinions and emotions. As a result, this study investigated the Jordanian community's perspectives and feelings on the transition from pure face-to-face education to blended education by examining related tweets in the post-COVID era. Specifically, using NLP Emotion detection and Sentiment Analysis approaches, as well as deep learning models. As a result of analyzing the collected tweets, 18.75% of studied Jordanian's community sample are dissatisfied (Anger and Hate), 21.25% are negative (Sad), 13% are Happy, and 24.50 percent are Neutral about it.

An enhanced approach for sentiment analysis based on meta-ensemble deep learning

Sentiment analysis, commonly known as “opinion mining,” aims to identify sentiment polarities in opinion texts. Recent years have seen a significant increase in the acceptance of sentiment analysis by academics, businesses, governments, and several other organizations. Numerous deep-learning efforts have been developed to effectively handle more challenging sentiment analysis problems. However, the main difficulty with deep learning approaches is that they require a lot of experience and hard work to tune the optimal hyperparameters, making it a tedious and time-consuming task. Several recent research efforts have attempted to solve this difficulty by combining the power of ensemble learning and deep learning. Many of these efforts have concentrated on simple ensemble techniques, which have some drawbacks. Therefore, this paper makes the following contributions: First, we propose a meta-ensemble deep learning approach to improve the performance of sentiment analysis. In this approach, we train and fuse baseline deep learning models using three levels of meta-learners. Second, we propose the benchmark dataset “Arabic-Egyptian Corpus 2” as an extension of a previous corpus. The corpus size has been increased by 10,000 annotated tweets written in colloquial Arabic on various topics. Third, we conduct several experiments on six benchmark datasets of sentiment analysis in different languages and dialects to evaluate the performance of the proposed meta-ensemble deep learning approach. The experimental results reveal that the meta-ensemble approach effectively outperforms the baseline deep learning models. Also, the experiments reveal that meta-learning improves performance further when the probability class distributions are used to train the meta-learners.

Sentiment Analysis in Multiple Languages: A Review of Current Approaches and Challenges

Sentiment analysis, the process of automatically identifying and extracting subjective information from text, has gained increasing attention in recent years due to its potential applications in a variety of fields. However, the task of sentiment analysis can be challenging when applied to texts in multiple languages, as it requires not only language-specific preprocessing and feature extraction techniques, but also the development and adaptation of machine learning models that are able to handle the complexities of different languages. This research paper provides an overview of the current approaches and challenges in sentiment analysis for multiple languages. This study begins by discussing the general principles and techniques of sentiment analysis, including the use of deep learning and machine learning methods, as well as the importance of feature selection and ethical considerations. It examines the specific challenges and approaches for sentiment analysis in various languages, including Arabic, Chinese, Russian, and English. The use of multimodal sentiment analysis and the potential applications of sentiment analysis in various domains, such as healthcare, social media, and customer service. At the end, this review highlights the potential of sentiment analysis in multiple languages and the need for further research to improve the accuracy and reliability of sentiment analysis models for a variety of languages and domains. Future work should also address the ethical concerns involved in the collection and use of sentiment analysis data, as well as the challenges of adapting models to new languages and domains.

A hybrid composite features based sentence level sentiment analyzer

&lt;div align="left"&gt;&lt;span lang="EN-US"&gt;Current lexica and machine learning based sentiment analysis approaches still suffer from a two-fold limitation. First, manual lexicon construction and machine training is time consuming and error-prone. Second, the prediction’s accuracy entails sentences and their corresponding training text should fall under the same domain. In this article, we experimentally evaluate four sentiment classifiers, namely Support Vector Machines, Naive Bayes, Logistic Regression and Random Forest. We quantify the quality of each of these models using three real-world datasets that comprise 50,000 movie reviews, 10,662 sentences, and 300 generic movie reviews. Specifically, we study the impact of a variety of natural language processing (NLP) pipelines on the quality of the predicted sentiment orientations. Additionally, we measure the impact of incorporating lexical semantic knowledge captured by WordNet on expanding original words in sentences. Findings demonstrate that the utilizing different NLP pipelines and semantic relationships impacts the quality of the sentiment analyzers. In particular, results indicate that coupling lemmatization and knowledge-based n-gram features proved to produce higher accuracy results. With this coupling, the accuracy of the support vector machine (SVM) classifier has improved to 90.43%, while it was 86.83%, 90.11%, 86.20%, respectively using the three other classifiers. &lt;/span&gt;&lt;/div&gt;

A new sentiment analysis method to detect and Analyse sentiments of Covid-19 moroccan tweets using a recommender approach.

Since the beginning of the covid-19 crisis, people from all over the world have used social media platforms to publish their opinions, sentiments, and ideas about the coronavirus epidemic and their news. Due to the nature of social networks, users share an immense amount of data every day in a freeway, which gives them the possibility to express opinions and sentiments about the coronavirus pandemic regardless of the time and the place. Moreover, The rapid number of exponential cases globally has become the apprehension of panic, fear, and anxiety among people. In this paper, we propose a new sentiment analysis approach to detect sentiments in Moroccan tweets related to covid-19 from March to October 2020. The proposed model is a recommender approach using the advantages of recommendation systems for classifying each tweet into three classes: positive, negative, or neutral. Experimental results show that our method gives good accuracy(86%) and outperforms the well-known machine learning algorithms. We find also that the sentiments of users changed from period to period, and that the evolution of the epidemiological situation in morocco affects the sentiments of users.

Eurocentric cultural theme parks in Japan: domestic tourists’ perspectives on place branding

ABSTRACT During the Bubble Economy era, cultural theme parks were constructed in rural Japan for economic rejuvenation. These cultural theme parks or gaikoku mura (foreign villages) embrace foreign cultures and landscapes rather than rollercoasters. They offer Japanese tourists the foreign travel experience adapted and modified for the Japanese market. Set within place-based branding, imaginaries, and authenticity, this paper compares the Eurocentric theme parks of Huis Ten Bosch in Nagasaki and Yufuin Floral Village in Oita. Opening in 1992, Huis Ten Bosch is a large-scale cultural theme park based on Nagasaki’s historical connection to the Netherlands. Recreating Dutch cities and landscapes, it offers hotels, restaurants, shops, and attractions. Within the hot springs area of Yufuin, the Floral Village opened in 2012, modelled after The Cotswolds, UK. Houses with storybook architecture contain souvenir shops and tea rooms featuring characters from British literature and Studio Ghibli anime. Based on site visits, photographic documentation, and qualitative sentiment analysis of comments written by visitors on TripAdvisor, the paper investigates the perceptions of Japanese tourists. They are positive about Huis Ten Bosch with developers having successfully created and branded a Dutch environment, while mixed messages at Yufuin demonstrate the importance of product-market match for these ‘exotic’ attractions.

Lexicon-based sentiment analysis in texts using Formal Concept Analysis

In this paper, we present a novel approach for sentiment analysis that uses Formal Concept Analysis (FCA) to create dictionaries for classification. Unlike other methods that rely on pre-defined lexicons, our approach allows for the creation of customised dictionaries that are tailored to the specific data and tasks. By using a dataset of tweets categorised into positive and negative polarity, we show that our approach achieves a better performance than other standard dictionaries.